[PATCH v4 1/6] drm/amdgpu/aca: Fix race condition and UAF in error cache logging

[Sreeraj S Kurup <sreekuttan2156239@gmail.com>]

In aca_error_cache_log_bank_error(), find_bank_error() released
aerr->lock prior to returning bank_error. This created a time-of-check
to time-of-use (TOCTOU) race window where a concurrent caller of
aca_log_aca_error() could acquire aerr->lock and free the bank_error
node via aca_bank_error_remove().

When execution returned to aca_error_cache_log_bank_error(),
incrementing bank_error->count resulted in a Use-After-Free and
potential kernel memory corruption. Additionally, bank_error->count
was updated outside mutex lock protection.

Fix this by acquiring aerr->lock at the start of
aca_error_cache_log_bank_error() and holding it continuously across
lookup, creation, and counter updates, while removing redundant
internal lock acquisitions in helper functions.

Signed-off-by: Sreeraj S Kurup <sreekuttan2156239@gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c | 18 +++++++-----------
 1 file changed, 7 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index db7858fe0c3d..d0d473082431 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -237,10 +237,8 @@ static struct aca_bank_error *new_bank_error(struct aca_error *aerr, struct aca_
 	INIT_LIST_HEAD(&bank_error->node);
 	memcpy(&bank_error->info, info, sizeof(*info));
 
-	mutex_lock(&aerr->lock);
 	list_add_tail(&bank_error->node, &aerr->list);
 	aerr->nr_errors++;
-	mutex_unlock(&aerr->lock);
 
 	return bank_error;
 }
@@ -249,22 +247,16 @@ static struct aca_bank_error *find_bank_error(struct aca_error *aerr, struct aca
 {
 	struct aca_bank_error *bank_error = NULL;
 	struct aca_bank_info *tmp_info;
-	bool found = false;
 
-	mutex_lock(&aerr->lock);
 	list_for_each_entry(bank_error, &aerr->list, node) {
 		tmp_info = &bank_error->info;
 		if (tmp_info->socket_id == info->socket_id &&
 		    tmp_info->die_id == info->die_id) {
-			found = true;
-			goto out_unlock;
+			return bank_error;
 		}
 	}
 
-out_unlock:
-	mutex_unlock(&aerr->lock);
-
-	return found ? bank_error : NULL;
+	return NULL;
 }
 
 static void aca_bank_error_remove(struct aca_error *aerr, struct aca_bank_error *bank_error)
@@ -306,11 +298,15 @@ int aca_error_cache_log_bank_error(struct aca_handle *handle, struct aca_bank_in
 		return 0;
 
 	aerr = &error_cache->errors[type];
+	mutex_lock(&aerr->lock);
 	bank_error = get_bank_error(aerr, info);
-	if (!bank_error)
+	if (!bank_error) {
+		mutex_unlock(&aerr->lock);
 		return -ENOMEM;
+	}
 
 	bank_error->count += count;
+	mutex_unlock(&aerr->lock);
 
 	return 0;
 }
-- 
2.54.0